HumRightsBench - Issue Identification (I1): leaderboard
HumRightsBench (2026) is a pilot, expert-validated benchmark of reasoning in international human rights law built on right-to-water scenarios and structured along issue identification, rule recall, rule application and proposed remedies. This board is the first issue-identification multiple-choice question per sub-scenario, asking which failure or obligation violation is most clearly engaged. Accuracy in percent over five seeds; higher is better.
Metric: Accuracy (%; x100 of the exact-set match rate on the first issue-identification multiple-choice question per sub-scenario: which failure or obligation violation is most clearly engaged; pilot HumRightsBench question set on right-to-water scenarios validated by human rights experts; each question asked with five seeds and shuffled answer order (Qwen 3.5-9B multiple-choice types over four), responses through each provider's structured-output interface, errored calls counted as incorrect). Source: arxiv.org. Saturation forecast: Around November 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 54 | #141 |
| 2 | GPT-5 | 52 | #163 |
| 3 | Claude Opus 4.7 | 47.3 | #75 |
| 4 | Qwen 3.5 9B | 39.4 | #803 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=humrightsbench-issue-identification-i1 · How It Works · Data refreshed daily, snapshot 2026-11-12.